Fine-Tuning TransMorph with Gradient Correlation for Anatomical Alignment

TL;DR

This paper introduces a fine-tuning approach for the TransMorph model using gradient correlation and a specialized optimizer to enhance brain MRI registration accuracy, smoothness, and structural consistency.

Contribution

It presents a novel fine-tuning method incorporating gradient correlation and FAdam optimizer to improve anatomical alignment in MRI registration.

Findings

Slight improvements in Dice and HdDist95 scores.

Significant reduction in NDV.

Enhanced deformation smoothness and structural consistency.

Abstract

Unsupervised deep learning is a promising method in brain MRI registration to reduce the reliance on anatomical labels, while still achieving anatomically accurate transformations. For the Learn2Reg2024 LUMIR challenge, we propose fine-tuning of the pre-trained TransMorph model to improve the convergence stability as well as the deformation smoothness. The former is achieved through the FAdam optimizer, and consistency in structural changes is incorporated through the addition of gradient correlation in the similarity measure, improving anatomical alignment. The results show slight improvements in the Dice and HdDist95 scores, and a notable reduction in the NDV compared to the baseline TransMorph model. These are also confirmed by inspecting the boundaries of the tissue. Our proposed method highlights the effectiveness of including Gradient Correlation to achieve smoother and structurally consistent deformations for interpatient brain MRI registration.